{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T13:29:45Z","timestamp":1745328585839,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031262920"},{"type":"electronic","value":"9783031262937"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26293-7_6","type":"book-chapter","created":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T20:02:47Z","timestamp":1678478567000},"page":"88-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Gated Cross Word-Visual Attention-Driven Generative Adversarial Networks for\u00a0Text-to-Image Synthesis"],"prefix":"10.1007","author":[{"given":"Borun","family":"Lai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,11]]},"reference":[{"key":"6_CR1","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, Montreal, Canada, pp. 2672\u20132680, December 2014"},{"key":"6_CR2","unstructured":"Gregor, K., Danihelka, I., Graves, A.: DRAW: a recurrent neural network for image generation. In: International Conference on Machine Learning, Lille, France, pp. 1462\u20131471, July 2015"},{"key":"6_CR3","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Advances in Neural Information Processing Systems, Long Beach, CA, USA, pp. 6626\u20136637, December 2017"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.: Attention on attention for image captioning. In: IEEE\/CVF International Conference on Computer Vision, Seoul, Korea, pp. 4633\u20134642, October 2019","DOI":"10.1109\/ICCV.2019.00473"},{"key":"6_CR5","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, vol. 5, San Diego, CA, May 2015"},{"key":"6_CR6","unstructured":"Li, B., Qi, X., Lukasiewicz, T., Torr, P.: Controllable text-to-image generation. In: Advances in Neural Information Processing Systems, Vancouver, BC, Canada, pp. 2065\u20132075, December 2019"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Li, W.: Object-driven text-to-image synthesis via adversarial training. In: IEEE International Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, pp. 12166\u201312174, June 2019","DOI":"10.1109\/CVPR.2019.01245"},{"issue":"3","key":"6_CR8","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1007\/s11760-021-02020-2","volume":"16","author":"W Li","year":"2022","unstructured":"Li, W., Zhu, H., Yang, S., Zhang, H.: DADAN: dual-path attention with distribution analysis network for text-image matching. SIViP 16(3), 797\u2013805 (2022). https:\/\/doi.org\/10.1007\/s11760-021-02020-2","journal-title":"SIViP"},{"key":"6_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"5","key":"6_CR10","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1007\/s11760-021-02063-5","volume":"16","author":"Z Lu","year":"2022","unstructured":"Lu, Z., Chen, Y.: Single image super-resolution based on a modified U-net with mixed gradient loss. SIViP 16(5), 1143\u20131151 (2022). https:\/\/doi.org\/10.1007\/s11760-021-02063-5","journal-title":"SIViP"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J.: Context encoders: feature learning by inpainting. In: IEEE International Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 2536\u20132544, June 2016","DOI":"10.1109\/CVPR.2016.278"},{"key":"6_CR12","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: Learn, imagine and create: text-to-image generation from prior knowledge. In: Neural Information Processing Systems (2019)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Qiao, T., Zhang, J., Xu, D., Tao, D.: MirrorGAN: learning text-to-image generation by redescription. In: IEEE International Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, pp. 1505\u20131514, June 2019","DOI":"10.1109\/CVPR.2019.00160"},{"key":"6_CR14","unstructured":"Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw, New Republic (2016)"},{"key":"6_CR15","unstructured":"Reed, S.E., Akata, Z., Yan, X.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, New York City, NY, USA, pp. 1060\u20131069, June 2016"},{"key":"6_CR16","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Xi, C.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, Barcelona, Spain, pp. 2234\u20132242, December 2016"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Tan, H., Liu, X., Li, X., Zhang, Y., Yin, B.: Semantics-enhanced adversarial nets for text-to-image synthesis. In: IEEE\/CVF International Conference on Computer Vision, Seoul, Korea, pp. 10500\u201310509, October 2019","DOI":"10.1109\/ICCV.2019.01060"},{"key":"6_CR18","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1109\/TIP.2020.3026728","volume":"30","author":"X Tan","year":"2021","unstructured":"Tan, X., Liu, M., Yin, B., Li, X.: KT-GAN: knowledge-transfer generative adversarial network for text-to-image synthesis. IEEE Trans. Image Process. 30, 1275\u20131290 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR19","unstructured":"Tao, M., et al.: DF-GAN: deep fusion generative adversarial networks for text-to-image synthesis. arXiv preprint arXiv:2008.05865 (2020)"},{"key":"6_CR20","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset. Technical report CNS-TR-2011-001, California Institute of Technology (2011)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Z., Quan, Z., Wang, Z.J., Hu, X., Chen, Y.: Text to image synthesis with bidirectional generative adversarial network. In: IEEE International Conference on Multimedia and Expo, London, UK, pp. 1\u20136, July 2020","DOI":"10.1109\/ICME46284.2020.9102904"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Xu, T.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: IEEE International Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 1316\u20131324, June 2018","DOI":"10.1109\/CVPR.2018.00143"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Yin, G., Liu, B., Sheng, L., Yu, N., Wang, X., Shao, J.: Semantics disentangling for text-to-image generation. In: IEEE International Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, pp. 2322\u20132331, June 2019","DOI":"10.1109\/CVPR.2019.00243"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: IEEE International Conference on Computer Vision, Venice, Italy, pp. 5907\u20135915, October 2017","DOI":"10.1109\/ICCV.2017.629"},{"issue":"8","key":"6_CR25","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2019","unstructured":"Zhang, H., et al.: StackGAN++: realistic image synthesis with stacked generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 41(8), 1947\u20131962 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, Y., Yang, L.: Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00649"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, M., Pan, P., Chen, W., Yang, Y.: DM-GAN: dynamic memory generative adversarial networks for text-to-image synthesis. In: IEEE International Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, pp. 5795\u20135803, June 2019","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26293-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T20:04:07Z","timestamp":1678478647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26293-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031262920","9783031262937"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26293-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"11 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.accv2022.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT Microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"836","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"277","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the ACCV 2022 workshops 25 papers have been accepted from 40 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}